High Performance Computing - ISC High Performance Digital 2021 International Workshops, Frankfurt am Main, Germany, June 24 - July 2, 2021, Revised Selected Papers
High Performance Computing - ISC High Performance Digital 2021 International Workshops, Frankfurt am Main, Germany, June 24 - July 2, 2021, Revised Selected Papers
复制标题
高性能计算 - ISC 高性能数字 2021 国际研讨会，德国美因河畔法兰克福，2021 年 6 月 24 日至 7 月 2 日，修订后的精选论文
DOI：
10.1007/978-3-030-90539-2_4
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Nogueira A
中科院分区：
文献类型：
--
作者：
Nogueira A
混沌的数学概念是由爱德华·洛伦兹在20世纪60年代早期提出的，当时他正试图通过垂直方向施加温差的二维流体流动来表示大气对流。从那时起，混沌动力系统被认为是气象科学的基础，是天气和气候预报工具不可或缺的试验台。可操作的天气预报平台依赖于昂贵的基于偏微分方程（PDE）的模型，这些模型在高性能计算架构上连续运行。基于机器学习（ML）的低维代理模型可以被视为这种高保真仿真平台的经济有效的解决方案。在这项工作中，我们提出了一种基于水库计算-回声状态神经网络（RC-ESN）的机器学习方法来准确预测混沌系统的进化状态。我们从基线Lorenz-63和96系统开始，并表明RC-ESN在使用Pearson交叉相关相似性度量一致预测时间序列方面非常有效。RC-ESN可以准确地预测未来许多李雅普诺夫时间单位的洛伦兹系统。在一个实际的数值例子中，我们将RC-ESN结合仅空间正交分解（POD）建立了一个降阶模型（ROM），该模型可以对美国大陆地区的污染扩散进行连续的短期预测。我们使用GEOS-CF模拟数据来评估我们的RC-ESN ROM。数值实验表明，对于如此高度复杂的大气污染系统，结果是合理的。
The mathematical concept of chaos was introduced by Edward Lorenz in the early 1960s while attempting to represent atmospheric convection through a two-dimensional fluid flow with an imposed temperature difference in the vertical direction. Since then, chaotic dynamical systems are accepted as the foundation of the meteorological sciences and represent an indispensable testbed for weather and climate forecasting tools. Operational weather forecasting platforms rely on costly partial differential equations (PDE)-based models that run continuously on high performance computing architectures. Machine learning (ML)-based low-dimensional surrogate models can be viewed as a cost-effective solution for such high-fidelity simulation platforms. In this work, we propose an ML method based on Reservoir Computing - Echo State Neural Network (RC-ESN) to accurately predict evolutionary states of chaotic systems. We start with the baseline Lorenz-63 and 96 systems and show that RC-ESN is extremely effective in consistently predicting time series using Pearson’s cross correlation similarity measure. RC-ESN can accurately forecast Lorenz systems for many Lyapunov time units into the future. In a practical numerical example, we applied RC-ESN combined with space-only proper orthogonal decomposition (POD) to build a reduced order model (ROM) that produces sequential short-term forecasts of pollution dispersion over the continental USA region. We use GEOS-CF simulated data to assess our RC-ESN ROM. Numerical experiments show reasonable results for such a highly complex atmospheric pollution system.